I’m running the notebook Instance Segmentation with Model Garden from Tensorflow Model Garden documentation. During the training, the output of the ‘Train and Evaluate’ periodically displays the metrics, but the value of the validation loss is always zero.
For example:
...
eval | step: 1200 | steps/sec: 3.3 | eval time: 60.0 sec | output:
{'AP': 0.0814979,
'AP50': 0.16509584,
'AP75': 0.07145937,
...
'mask_ARs': 0.0015765766,
'steps_per_second': 3.3340747415649394,
'validation_loss': 0.0}
...
I noticed the same behavior in official Semantic Segmentation tutorial. In this tutorial, the outputs are shown on the tutorial page: Semantic Segmentation with Model Garden | TensorFlow Core
Is this a TensorFlow Models bug? Do I need to set any training configuration variable to calculate the validation loss?